一种图像降噪方法及电子设备、存储介质
By utilizing the weighted optimization of DCT basis and DCT coefficients in image denoising, the problems of poor denoising effect and high computational cost in existing technologies are solved, achieving efficient image denoising that is applicable to multiple application fields.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG DAHUA TECH CO LTD
- Filing Date
- 2023-10-25
- Publication Date
- 2026-07-17
AI Technical Summary
Existing image denoising techniques suffer from poor denoising performance and high computational costs, especially in frequency domain image denoising where the suppression of large noise is inadequate. Furthermore, deep learning algorithms require enormous computational resources, making them difficult to apply to practical products.
By determining weight parameters based on the differences between sub-blocks in the target image's noise-to-be region and the reference region, and using DCT basis and DCT coefficients for weighting, an energy function is constructed and the DCT coefficients are optimized to achieve effective image noise reduction while reducing computational costs.
It achieves effective noise reduction of images while reducing computational consumption, thereby improving image quality. It is applicable to fields such as biomedicine, military, traffic security, and machine vision.
Smart Images
Figure CN117575935B_ABST